tobjend 1d94c09344 experiment: CRX vs refined CRX across 3 codebases (Round 17) ... Refined wins 7/9 when producing useful grammars (model_cost >= 2). Trivial output (single symbol) in 5/13 cases on large groups. CRX wins only once (FastAPI tests, 3618 methods). Key finding: refined CRX is better ~78% of the time but needs triviality check (model_cost >= 2) to avoid single-symbol grammars.		2026-07-12 17:08:15 +02:00
..
results	feat: grammar_structure_score + min_structure filter	2026-07-12 03:02:50 +02:00
coarsen_eval.py	feat: 4-codebase evaluation — conventions vs completions tradeoff	2026-07-12 01:14:09 +02:00
context_eval.py	feat: implement Reduce algorithm (Algorithm 4, TODS 2010)	2026-07-12 00:11:38 +02:00
EXPERIMENT_LOG.md	experiment: CRX vs refined CRX across 3 codebases (Round 17)	2026-07-12 17:08:15 +02:00
freq_eval.py	feat: frequency threshold sweep — 0.01-0.20 across 4 codebases	2026-07-12 01:26:45 +02:00
gbnf_eval.py	perf: iDRegEx opt-in, GBNF newline fix, OverflowError fix	2026-07-12 02:52:05 +02:00
RESULTS.md	docs: experiment log + cross-package analysis	2026-07-12 00:45:21 +02:00